© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 57809
    Prev
    Next
    INDEX
    Explanations

    How to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸Ģ页
    -0.10
    unning
    -0.09
     Dak
    -0.09
    ϲ
    -0.09
     Schwartz
    -0.08
    龸
    -0.08
    åħ³çĪ±
    -0.08
    éħĭ
    -0.08
    主导
    -0.08
    æijĺ
    -0.08
    POSITIVE LOGITS
    éĹª
    0.08
     lanc
    0.08
    ych
    0.08
    -ed
    0.08
    zo
    0.08
    omite
    0.08
    è¤Ĭ
    0.07
    ç¨
    0.07
    Æ°a
    0.07
    æIJ¦
    0.07
    Activations Density 0.014%

    No Known Activations